AI Glossary

Agentic AI

Agentic AI describes AI systems designed to pursue goals through planning, tool use, decision making, memory, feedback, and sequences of actions with varying levels of autonomy.

AI Agent

Also known as: AI Agent System

An AI agent is a software system that uses an AI model to interpret goals, make decisions, use tools, perform actions, and potentially repeat steps in order to complete a task.

AI Automation

AI automation combines artificial intelligence with automated workflows so that systems can analyze information, generate outputs, classify data, make limited decisions, or trigger actions with reduced manual intervention.

AI Hallucination

Also known as: LLM Hallucination, Model Hallucination

An AI hallucination occurs when an AI system generates information that appears plausible but is unsupported, incorrect, fabricated, or inconsistent with reliable evidence.

AI Model

Also known as: Artificial Intelligence Model

An AI model is a computational system trained or configured to transform inputs into predictions, classifications, generated content, decisions, or other outputs.

API

Also known as: Application Programming Interface

An API, or Application Programming Interface, is a defined way for software systems to communicate and exchange requests, data, or functionality.

Artificial Intelligence (AI)

Also known as: AI, Artificial Intelligence

Artificial intelligence is the field of creating computer systems that can perform tasks associated with human intelligence, such as understanding language, recognizing patterns, making predictions, generating content, and supporting decisions.

Context Window

A context window is the amount of information an AI model can consider within a single interaction or processing session, typically measured in tokens.

Embedding

Also known as: Vector Embedding

An embedding is a numerical representation of data that captures meaningful relationships and similarity in a multidimensional vector space.

Few-Shot Prompting

Few-shot prompting is a technique in which an AI model is given a small number of examples demonstrating the desired task or output pattern before processing a new input.

Fine-Tuning

Fine-tuning is the process of further training an existing AI model on additional task-specific or domain-specific data to modify its behavior or capabilities.

Foundation Model

A foundation model is a broadly trained AI model that can support many downstream tasks and can often be adapted through prompting, retrieval, fine-tuning, or additional tools.

Generative AI

Also known as: GenAI, Generative Artificial Intelligence

Generative AI refers to artificial intelligence systems designed to create new content such as text, images, audio, video, software code, or structured data.

Inference

Inference is the process of using a trained AI or machine learning model to produce an output from new input data.

Large Language Model (LLM)

Also known as: LLM, Large Language Model

A large language model is an AI model trained on large amounts of text and other data to understand and generate language by predicting and producing sequences of tokens.

Machine Learning

Also known as: ML

Machine learning is a branch of artificial intelligence in which computer systems learn patterns from data and use those patterns to make predictions, classifications, recommendations, or other outputs.

Multimodal AI

Multimodal AI refers to systems that can process, understand, or generate more than one type of information, such as text, images, audio, video, or structured data.

Neural Network

Also known as: Artificial Neural Network, ANN

A neural network is a machine learning model composed of interconnected computational units arranged in layers that learn patterns and representations from data.

Prompt Engineering

Also known as: Prompt Design, AI Prompt Engineering

The practice of designing and improving instructions for generative AI systems.

Retrieval-Augmented Generation (RAG)

Also known as: RAG

Retrieval-augmented generation is an AI architecture that retrieves relevant information from external sources and supplies it to a generative model when producing a response.

System Prompt

A system prompt is a high-level instruction provided to an AI model that defines behavior, role, constraints, priorities, or operating rules for an interaction.

Token

A token is a unit of text or other input that an AI model processes, such as part of a word, a whole word, punctuation, or another encoded element.

Transformer

A transformer is a neural network architecture that processes relationships between elements in a sequence using attention mechanisms and forms the foundation of many modern language and multimodal AI models.

Vector Database

A vector database is a data system designed to store, index, and search numerical vector representations such as embeddings.

Zero-Shot Prompting

Zero-shot prompting is a prompting technique in which an AI model is asked to perform a task without being shown examples of the desired input-output behavior.